Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude Code
Drift doc-to-code anchor conventions. Use when editing code that is bound by drift docs, updating docs, working with drift.lock, or when drift check reports stale anchors.
Skill Claude CodeCodex
Upload local files to file.kiwi and get an instant shareable download link.
Skill Claude CodeCodex
De-escalate tense interactions using proven techniques. Use when user asks to 'de-escalate conflict', 'handle angry customer', 'calm tense situation', 'respond to aggression', 'reduce tension in conversation', 'de-fuse a volatile situation'.
Skill Claude CodeCodex
A local knowledge search tool for finding project decisions, documents, and relationships between people, concepts, events, and other project items across previous sessions.
Skill Claude CodeCodex
Find the best tool for your task across 22,000+ MCP servers and OpenClaw skills. Ranked by community trust. No API key.
Skill Claude CodeCodex
Use when a user wants to choose, change, compare, or improve the FONTS / typography of their web app — ANY framework: Next.js, Vite, Astro, Remix, SvelteKit, TanStack, plain CSS ("pick a font", "these fonts look generic/AI-generated", "make the headings nicer", "what typeface should I use", "change the font"). Font…
jonnybottles/patch-tuesday-mcp
Skill Claude CodeCodex
Monthly Patch Tuesday identity/security triage using the single msrcsearch tool with product watchlists.
Skill Claude CodeCodex
P4 Plan Find query syntax for advanced searching. Use when user needs to search, filter, or find items by status, assignee, priority, severity, dates, custom fields, or any combination.
Skill Claude Code
Use this skill when the user asks about finding x402-payable APIs, discovering payment endpoints for AI agents, searching for monetized API services, checking API trust scores or uptime, or verifying x402 attestations. Automatically surfaces relevant services from the x402 Service Discovery catalog with pricing, trust…
Skill Claude CodeCodex
Design-system workflow for FramingUI projects (free profile). Use for ANY UI work in a project that uses FramingUI — building or restyling screens, pages, components, layouts, or themes; writing AgenticLayoutContract JSON; choosing themes/tokens/icons; or reviewing FramingUI-based JSX. Triggers on requests like "build…
Skill Claude CodeCodex
Automatic context checkpointing via the ctxfile MCP tools. Use throughout every session - at session start (load context), when tasks complete or decisions are made (checkpoint), and when the user hands work off or says goodbye.
Skill Claude CodeCodex
Talk to another agent working the same plumb workspace — address a peer session by name, hand your turn over while waiting for its reply, and read silence correctly. Use when work has to be coordinated with a concurrent session.
levelsofself/mcp-nervous-system
Skill Claude CodeCodex
Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.
SomeStay07/claude-memory-skill
Skill Claude Code
Unified project memory management: update, prune, reflect, and maintain knowledge. Combines conversation scanning, deduplication, contradiction detection, confidence scoring, and consistency checks in a single skill. Usage: /memory update [topic] — scan conversation, persist learnings /memory prune [type] — find…
Skill Claude Code
Draft a pull-request message (title + Markdown body) for the current branch into main. Use when the user asks for a "PR message", "PR description", "pull request message", or says "write a PR message" / "give me a PR message". Output is Markdown text only — does not call gh or open a PR.
Skill Claude CodeCodex
Use when a Codex task should set up, inspect, or operate Yaver through the bundled MCP server.
Skill Claude Code
Recommends which Claude model and effort level to fit a task, using cost of error as the deciding signal. Use when asked which Claude model or effort to use, or a task feels over or underpowered.
Skill Claude Code
Build-DNA is a Claude skill that turns your skills, experiences, and unfair advantages into a business. Not another idea generator — your personal business brain. Use when someone wants to find a business idea, validate a startup concept, brainstorm products during a hackathon, figure out what to build as a side…
actual-software/actual-skill-openclaw
Skill Claude Code
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, and drives the Actual Advisor (login, advisor, whoami, logout) for org-scoped architecture questions. Covers all 5 runners (claude-cli…
Skill Claude CodeCodex
Use when a leading diagnosis or nontrivial fix has initial support and needs one adversarial counterexample before acceptance.
Skill Claude Code
Give an agent skill's decision logic a test suite and a deterministic implementation — a labeled validation dataset plus versionable Python — via an adversarial multi-persona loop that runs natively in Claude Code: proposer plus persona subagents through the Task tool, entirely on your Claude Code subscription, no…
Skill Claude Code
A project-workflow station that coordinates agents and skills from project setup through delivery, including requirements, design, task planning, scaffolding, and engineering workflows.
WESTsyre21/setup-backend-stack
Skill Claude CodeCodex
Bootstraps a local Node.js backend development stack with Docker, PostgreSQL, and an ORM (Prisma or Sequelize). Use this skill whenever the user wants to: initialize a new backend project, set up a Dockerized database locally, wire up an ORM with automated migrations, scaffold an Express server with a health endpoint…
DjordjeMojsilovic/Djordjes-Claude-Setup
Skill Claude CodeCodex
Use this skill whenever the user is building something with the Claude API and would benefit from a known-good reference implementation from Anthropic's official Claude Cookbooks. Trigger on any request that touches Claude API features — RAG, tool use, agents (Agent SDK or Managed Agents), vision/multimodal, prompt…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: